V
verygoodplugins/mcp-toggl
Time entries and reports in Toggl Track
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"verygoodplugins-mcp-toggl": {
"command": "npx",
"args": ["-y", "@verygoodplugins/mcp-toggl@latest"]
}
}
}解析自我们于 2026-11-05 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"verygoodplugins-mcp-toggl": {
"command": "npx",
"args": ["-y", "@verygoodplugins/mcp-toggl@latest"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio verygoodplugins-mcp-toggl -- npx -y @verygoodplugins/mcp-toggl@latest
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- 来源明细
- 收录自 abordage/awesome-mcp 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-11-05 · 最近见到 2026-11-14 · 共见到 10 次 · 被 10 个来源列出
- 评分构成
- 综合分 1,003 · 10 个来源 · mcp
- 安装
npx -y @verygoodplugins/mcp-toggl@latest
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
npx -y @verygoodplugins/mcp-toggl@latest。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
我们收录于 2026-11-05；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
# MCP Toggl
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
> Talk to your time tracking. Pull reports, start timers, inspect desktop activity, and turn raw Toggl data into useful recaps from Claude or any MCP-compatible client.
## See What Your Week Actually Looked Like
> You ask: "Give me the recap of my week"
The MCP server returns hydrated time entries with project, workspace, client, tag, and running-timer context. Your client can turn that into a readable recap:
> 32.7 hours across 31 entries and 7 projects. Monday was a light planning day, Tuesday had the long implementation block, Wednesday stayed focused on one project, and Friday turned into a shipping run. The top project took 27% of the week, with two smaller projects close behind.
The server does not hard-code this prose or chart. It exposes structured Toggl data in a shape that makes synthesis easy.
## Catch the Drift
> You ask: "Did I actually work on what I said I worked on for that PR review entry?"
togglgettimeline can compare a tracked entry boundary with Toggl Track Desktop activity:
> The entry ran 1h 33m. About 67 minutes were in review tools, 5 minutes were scattered across chat apps, and the rest was idle or trimmed timeline space. The entry mostly checks out.
This is useful before invoicing, after long context-switching days, or whenever a vague entry like "admin" starts hiding too much Slack and browser time.
## See Patterns Over Time
> You ask: "Show me last month at a glance"
Daily and weekly report tools make it straightforward for the client to render heatmaps, spot streaks, and surface intensity changes:
Toggl is still the source of truth. The MCP layer makes the data easier for an agent to inspect, summarize, and visualize.
## Things You Can Ask
text
What am I currently tracking?
How much time did I spend on the website project this month?
Start a timer for "PR review" on the Platform project
Show me yesterday's hours as a chart
What apps did I use most today?
Generate a daily report for last Friday
Compare this week to last week by project
Which day this month had the most billable work?
Chart prompts depend on your MCP client. The server returns the structured data; clients such as Claude decide how to render it.
## What Makes This Useful
Hydrated responses: time entries are enriched with projectname, clientname, workspacename, tagnames, and normalized running-timer fields so the client does not need a second lookup for ordinary reporting.
Smart caching: workspaces, projects, clients, tasks, and tags are cached after first read. togglcachestats shows hits, misses, loaded entities, and hit rate.
Desktop activity timeline: togglgettimeline summarizes app usage from Toggl Track Desktop and can return raw events when you need sequence analysis.
Privacy controls: timeline calls support summary-only output with includeevents: false and title redaction with redacttitles: true.
Period shortcuts: today, yesterday, week, lastWeek, month, and lastMonth are supported on the tools where those periods make sense.
Recoverable errors: workspace resolution errors include availableworkspaces, and Toggl quota/rate-limit errors include structured retry hints.
## Quick Start
### Prerequisites
Node.js ^20.19.0 or >=22.12.0
## See What Your Week Actually Looked Like
> You ask: "Give me the recap of my week"
The MCP server returns hydrated time entries with project, workspace, client, tag, and running-timer context. Your client can turn that into a readable recap:
> 32.7 hours across 31 entries and 7 projects. Monday was a light planning day, Tuesday had the long implementation block, Wednesday stayed focused on one project, and Friday turned into a shipping run. The top project took 27% of the week, with two smaller projects close behind.
The server does not hard-code this prose or chart. It exposes structured Toggl data in a shape that makes synthesis easy.
## Catch the Drift
> You ask: "Did I actually work on what I said I worked on for that PR review entry?"
togglgettimeline can compare a tracked entry boundary with Toggl Track Desktop activity:
> The entry ran 1h 33m. About 67 minutes were in review tools, 5 minutes were scattered across chat apps, and the rest was idle or trimmed timeline space. The entry mostly checks out.
This is useful before invoicing, after long context-switching days, or whenever a vague entry like "admin" starts hiding too much Slack and browser time.
## See Patterns Over Time
> You ask: "Show me last month at a glance"
Daily and weekly report tools make it straightforward for the client to render heatmaps, spot streaks, and surface intensity changes:
Toggl is still the source of truth. The MCP layer makes the data easier for an agent to inspect, summarize, and visualize.
## Things You Can Ask
text
What am I currently tracking?
How much time did I spend on the website project this month?
Start a timer for "PR review" on the Platform project
Show me yesterday's hours as a chart
What apps did I use most today?
Generate a daily report for last Friday
Compare this week to last week by project
Which day this month had the most billable work?
Chart prompts depend on your MCP client. The server returns the structured data; clients such as Claude decide how to render it.
## What Makes This Useful
Hydrated responses: time entries are enriched with projectname, clientname, workspacename, tagnames, and normalized running-timer fields so the client does not need a second lookup for ordinary reporting.
Smart caching: workspaces, projects, clients, tasks, and tags are cached after first read. togglcachestats shows hits, misses, loaded entities, and hit rate.
Desktop activity timeline: togglgettimeline summarizes app usage from Toggl Track Desktop and can return raw events when you need sequence analysis.
Privacy controls: timeline calls support summary-only output with includeevents: false and title redaction with redacttitles: true.
Period shortcuts: today, yesterday, week, lastWeek, month, and lastMonth are supported on the tools where those periods make sense.
Recoverable errors: workspace resolution errors include availableworkspaces, and Toggl quota/rate-limit errors include structured retry hints.
## Quick Start
### Prerequisites
Node.js ^20.19.0 or >=22.12.0
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/verygoodplugins-mcp-toggl/)
- 来源
- awesome · https://github.com/verygoodplugins/mcp-toggl
- 按领域浏览
- MCP 服务
- 收录来源
- 10 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。